grepai-embeddings-openai

This skill covers using OpenAI's embedding API with GrepAI for high-quality, cloud-based embeddings. Get your API key at: Set the environment variable: Warning: Never commit API keys to version control. Best for: Most use cases, good balance of cost/quality. Best for: Maximum accuracy, cost not a concern. You can reduce dimensions to save storage: Approximate costs per 1000 source files: Note: Costs are one-time for initial indexing. Updates only re-embed changed files. GrepAI v0.24.0+ supports adaptive rate limiting and parallel requests: Parallelism recommendations: GrepAI automatically batches chunks for efficient API usage. OpenAI has rate limits based on your account tier: GrepAI handles rate limiting automatically with adaptive backoff. macOS/Linux: Windows (PowerShell): Create .env in your project root: Add to .gitignore : For Azure-hosted OpenAI: ❌ Problem: 401 Unauthorized ✅ Solution: Check API key is correct and environment variable is set: ❌ Problem: 429 Rate limit exceeded ✅ Solution: Reduce parallelism or upgrade OpenAI tier: ❌ Problem: High costs ✅ Solutions: ❌ Problem: Slow indexing ✅ Solution: Increase parallelism: ❌ Problem: Privacy concerns ✅ Solution: Use Ollama for local embeddings instead Important: You cannot mix embeddings from different models/providers.